Shuhei Ikemoto

Reconstructing Backpropagation from Forward Fluctuations in Noise-modulated Neural Networks

It is shown that backpropagation itself can be reconstructed in the NNN from forward-pass statistics alone: a weight mirror estimates each weight matrix from the covariance between a previous-layer unit's output and the next-layer unit's input, and combining it with local differential estimation inside the units propag...